Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific details or direct instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    |।
    0.36
     SUVs
    0.34
    tır
    0.34
     mêmes
    0.34
     gyms
    0.34
     aynı
    0.33
    માં
    0.33
    tı
    0.33
    tahun
    0.33
     ISPs
    0.33
    POSITIVE LOGITS
    i
    0.32
    ↵
    0.32
    ong
    0.31
    in
    0.30
    7
    0.29
    er
    0.29
     For
    0.27
     for
    0.26
    6
    0.26
    ur
    0.26
    Act Density 1.428%

    No Known Activations